Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    chat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्ञ
    -0.08
    ↵
↵
↵
    -0.07
     Lyons
    -0.07
    _fre
    -0.06
    pte
    -0.06
    lib
    -0.06
     integrating
    -0.06
     sanctioned
    -0.06
    .Look
    -0.06
    "↵↵↵↵
    -0.06
    POSITIVE LOGITS
     Destination
    0.07
     wrongful
    0.07
     extra
    0.07
     Blvd
    0.07
    .Enabled
    0.06
     jouer
    0.06
    écial
    0.06
    طح
    0.06
     Yardım
    0.06
    _exception
    0.06
    Act Density 0.000%

    No Known Activations